CASE STUDY - 2 :: Apple Foliar Disease Detection 🍎🌳🍏

img_1



PROJECT Documents 💼

Business Deck

DATASETS Used 🍃

NOTEBOOK Description 📗

NOTEBOOK Contents ✍️

1. Libraries Import

2. Dataset Import

Target Label Data Distributions

Q1a. What is the distribution of plant diseases in the TRAIN images of Plant Pathology Dataset 2020❓

Q1b. Does multiple diseases target label in the dataset means infected from both RUST & SCAB in Plant Pathology Dataset 2020❓

Q1c. Does un-healthy target label in the dataset means infected from either one or multiples diseases❓

Displaying some images of each target disease category

Q2a. Let's visualize some of the images that belongs to HEALTHY class❓

Q2b. Let's visualize some of the images that belongs to MULTIPLE DISEASES class❓

Q2c. Let's visualize some of the images that belongs to RUST class❓

Q2d. Let's visualize some of the images that belongs to SCAB class❓

Finding duplicate images in the dataset

Q3a. Do we have any duplicate images in the entire dataset❓

View all images channels distribution

Q4. What are the distributions of the RGB channels in the TRAIN & TEST images❓

Pixel values change in intensity for infected portions

Q5. Do we have any significant change in the intensities of the channels in infected images❓

Import_Libraries

Dataset_Import

Target Label Data Distributions

Q1a.

What is the distribution of plant diseases in the TRAIN images of Plant Pathology Dataset 2020

OBSERVATION

From the above plot, we came to know that:

OBSERVATION

Q1b.

Does multiple diseases target label in the dataset means infected from both RUST & SCAB in Plant Pathology Dataset 2020

OBSERVATION

Q1c.

Does un-healthy target label in the dataset means infected from either one or multiples diseases❓

OBSERVATION

OBSERVATION

Displaying some images of each target disease category

Q2a.

Let's visualize some of the images of HEALTHY class❓

OBSERVATION

From the above plot, we came to know that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

Q2b.

Let's visualize some of the images of MULTIPLE DISEASES class❓

OBSERVATION

From the above plot, we came to know that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

From the above images, we can say that:

OBSERVATION

This image is quite interesting:

OBSERVATION

In the above image, we found that:

Q2c.

Let's visualize some of the images of RUST class❓

OBSERVATION

From the above plot, we came to know that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

Q2d.

Let's visualize some of the images of SCAB class❓

OBSERVATION

From the above plot, we came to know that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

OBSERVATION

In the above image, we found that:

Finding duplicate images in the dataset

Q3a.

Let's check how many duplicate images we have in the dataset❓

OBSERVATION - 1

🤔 In the above analysis, we found that the 2 images Train_592.jpg & Train_782.jpg appears to be identical, however, there md5 codes are different.

OBSERVATION - 2

REASONING

View all images channels distribution

Q4.

What are the distributions of the RGB channels in the TRAIN & TEST images❓

REASONING

📊 ALL (TRAIN + TEST) Images

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

📊TRAIN Images

📊HEALTHY :: TRAIN Images

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

📊MULTIPLE DISEASES :: TRAIN Images

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

📊RUST DISEASES :: TRAIN Images

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

📊SCAB DISEASES :: TRAIN Images

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

OBSERVATION

Pixel values change in intensity for infected portions

Q5.

Do we have any significant change in the intensities of the channels in infected images❓

OBSERVATION

MD_Img

OBSERVATION

RU_Img

OBSERVATION

SC_Img

SUMMARY